ClawHub
Back to skill

Security audit

Pine Script Strategy Builder

Security checks for vulnerabilities and agentic risk

Overview

This skill is a TradingView Pine Script coding helper with disclosed, purpose-aligned examples and no hidden install, persistence, credential, or network behavior.

Install only if you want help generating TradingView Pine Script. Treat generated strategies as financial-risk code: review the logic, backtest it, and be especially careful before connecting alerts or broker automation to any entries, exits, or close-all behavior.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger description is unusually broad and includes generic phrases such as 'write a strategy', 'create indicator', and 'backtest this', which can cause the skill to activate for loosely related or ambiguous user requests. Over-broad activation increases the chance this trading-focused skill handles requests outside its intended scope, leading to inappropriate code generation or unsafe financial guidance in contexts where a more suitable skill should respond.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 26)May include surrounding context.

md
- Wrap signals in `barstate.isconfirmed`
- `strategy()` must have `calc_on_every_tick=false`, `process_orders_on_close=false`
- `request.security()` → use `barmerge.gaps_off, barmerge.lookahead_on` with `[1]` offset
- NEVER use current bar data for signal generation without confirmation

### Risk Management (ALWAYS)
- Every trade MUST have a stop loss — no naked positions

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

This markdown file includes executable Pine Script examples that perform safety-critical trading actions, including strategy.close_all(), which can materially affect a user's positions or results. The surrounding documentation does not warn users that these snippets can trigger automatic exits or alter live/paper trading behavior if adopted.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.